CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels

Documenti analoghi

• DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
  di: Qiang, Xinwei, et al.
  Pubblicazione: (2026)
• ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
  di: Luo, Xinhao, et al.
  Pubblicazione: (2025)
• Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
  di: Guan, Yue, et al.
  Pubblicazione: (2025)
• Design the Quantum Instruction Set with the Cartan Coordinate Analysis Framework
  di: Wu, Anbang, et al.
  Pubblicazione: (2024)
• VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference
  di: Liu, Zihan, et al.
  Pubblicazione: (2025)